hermes - 💡(How to fix) Fix SSE streaming: response.completed never sent due to race condition with agent_task.done()

Bug

When streaming via /v1/responses or /v1/chat/completions, the SSE loop relies on agent_task.done() to detect completion when the queue is empty. However, _on_delta filters out None (the agent's native EOS signal), so the loop can only exit via agent_task.done() — which can race with the queue-timeout check, causing keepalive messages to be sent indefinitely until the client disconnects.

Reproduction

1. Start the gateway
2. curl -sN http://127.0.0.1:8642/v1/responses -H "Content-Type: application/json" -d '{"input":"say hello","stream":true}'
3. Observe that response.completed is sometimes never sent; the stream just sends : keepalive every 30 seconds

Fix

In gateway/platforms/api_server.py, after creating agent_task, add a done callback that pushes a None sentinel to the queue:

agent_task = asyncio.ensure_future(self._run_agent(...))
agent_task.add_done_callback(lambda _: _stream_q.put(None))

Apply at both streaming paths:

• /v1/responses path (~line 2188)
• /v1/chat/completions path (~line 1160)

The None sentinel is safe because _on_delta filters None from agent callbacks, and the callback fires after the task completes (all agent callbacks have returned).